770 lines
38 KiB
Python
770 lines
38 KiB
Python
"""Board 3 „Guide": one card per block, linear stages with gates between them.
|
||
|
||
lernziele judge-Rolle Backward Design — objectives BEFORE writing
|
||
zuweisung code chapter/order from the outline artefact + facts grounding
|
||
writer guide-Rolle ONE coherent per-block text, only from VERIFIED FACTS
|
||
pruefer judge-Rolle EIN Call: CoVe-Fakten + Coverage + Lesbarkeit (lasen vorher
|
||
denselben Text in 3 seriellen Calls) + deterministische Gates
|
||
fix guide-Rolle EIN Rewrite unter allen Auflagen; bei falsch/Lücken danach
|
||
genau ein Re-Prüfer-Pass (der alte Lese-Fix blieb ungeprüft)
|
||
|
||
Runner: one asyncio task per card (cards are fixed from the start — no queue engine
|
||
needed); stage transitions are persisted in guide_cards, so the board is live and
|
||
cancel/resume just picks cards up at their stored stage. Assembly keeps the exact
|
||
legacy content format → content_fuer_level / TopicDetail stay untouched.
|
||
"""
|
||
|
||
import asyncio
|
||
import json
|
||
import logging
|
||
import re
|
||
|
||
import database as db
|
||
import readability
|
||
from blocks import _sink_json
|
||
from config import (FORMAT_PURPOSE, READABILITY_ACTIVE,
|
||
TEMPLATES_DIR, MAX_CONCURRENT_AGENTS_PER_TOPIC)
|
||
from guide_qa import block_budget
|
||
from fsutil import atomic_write_json
|
||
from jsonio import read_json_file as _json_file
|
||
from pipeline import (CANCELLED, FAILED, OK, GenContext, _extra, _log, _prompt,
|
||
_timeout, is_guide_cancelled, run_single_slot)
|
||
from textkit import _norm_title, _parse_fragment, _title
|
||
|
||
log = logging.getLogger("creator.guide_board")
|
||
|
||
GUIDE_STAGES = ("lernziele", "zuweisung", "writer", "pruefer", "fix")
|
||
STAGE_LABELS = {"lernziele": "Lernziele", "zuweisung": "Zuweisung", "writer": "Writer",
|
||
"pruefer": "Prüfen", "fix": "Fix", "done": "Fertig"}
|
||
from config import GATE_FIX_MIN, WRITER_SPLIT_SUBS # zentral tunebar
|
||
# Simultaneous cards = the per-topic agent cap: every card busies exactly ONE agent at a
|
||
# time (its stages run serially), so a lower number just idles slots (was hardcoded 10
|
||
# from the old 10-slot era while the .env already allowed 24).
|
||
CARD_CONCURRENCY = MAX_CONCURRENT_AGENTS_PER_TOPIC
|
||
|
||
|
||
def _safe(norm: str) -> str:
|
||
return re.sub(r"\W+", "_", norm)[:50] or "block"
|
||
|
||
|
||
def _ziele_schema(data):
|
||
"""{"ziele":[{id,text,sub}]} → list of dicts · None on invalid structure."""
|
||
if not isinstance(data, dict) or not isinstance(data.get("ziele"), list) or not data["ziele"]:
|
||
return None
|
||
out, seen = [], set()
|
||
for z in data["ziele"]:
|
||
if not isinstance(z, dict):
|
||
return None
|
||
zid = str(z.get("id", "")).strip()
|
||
text = str(z.get("text", "")).strip()
|
||
if not zid or not text or zid in seen or len(out) >= 12:
|
||
continue
|
||
seen.add(zid)
|
||
out.append({"id": zid, "text": text, "sub": str(z.get("sub", "")).strip()})
|
||
return out or None
|
||
|
||
|
||
def _gate_schema(data):
|
||
"""{"ok":true} → [] · {"claims":[{text,grund,urteil}]} → list · None invalid.
|
||
urteil "falsch" (contradicts the facts/itself) vs "unbelegt" (true but underivable) —
|
||
default unbelegt. Entries whose grund starts with "belegt" are dropped: one judge
|
||
returned a 65-entry full inventory including SUPPORTED claims."""
|
||
if not isinstance(data, dict):
|
||
return None
|
||
if data.get("ok") is True:
|
||
return []
|
||
claims = data.get("claims")
|
||
if not isinstance(claims, list) or not claims:
|
||
return None
|
||
out = []
|
||
for c in claims:
|
||
if isinstance(c, dict) and str(c.get("text", "")).strip():
|
||
grund = str(c.get("grund", "")).strip()
|
||
if grund.casefold().startswith("belegt"):
|
||
continue
|
||
urteil = str(c.get("urteil", "")).strip().casefold()
|
||
out.append({"text": str(c["text"]).strip(), "grund": grund,
|
||
"urteil": urteil if urteil == "falsch" else "unbelegt"})
|
||
return out
|
||
|
||
|
||
def _pruefer_schema(data, ziel_ids: set[str]):
|
||
"""Verschmolzenes Prüfer-Verdikt: Claims (Fakten-Gate-Semantik via _gate_schema) +
|
||
Coverage (ziele/luecken/ballast) + Lesbarkeit (lese_probleme). {"ok":true} = leeres
|
||
Verdikt. `ziele` muss alle ids abdecken, wenn Ziele existieren — sonst optional."""
|
||
if not isinstance(data, dict):
|
||
return None
|
||
if data.get("ok") is True:
|
||
return {"claims": [], "ziele": {}, "luecken": [], "ballast": [], "lese_probleme": []}
|
||
if not any(k in data for k in ("claims", "ziele", "luecken", "ballast", "lese_probleme")):
|
||
return None
|
||
claims = _gate_schema({"claims": data["claims"]}) if data.get("claims") else []
|
||
if claims is None:
|
||
return None
|
||
ziele = {}
|
||
for k, v in (data.get("ziele") or {}).items() if isinstance(data.get("ziele"), dict) else []:
|
||
ziele[str(k)] = str(v).strip().casefold() in ("true", "ja", "yes", "1")
|
||
if ziel_ids and not ziel_ids <= set(ziele):
|
||
return None
|
||
luecken = [{"ziel": str(l.get("ziel", "")), "fehlt": str(l.get("fehlt", ""))}
|
||
for l in data.get("luecken", []) if isinstance(l, dict) and str(l.get("fehlt", "")).strip()]
|
||
ballast = [str(b).strip() for b in data.get("ballast", []) if str(b).strip()]
|
||
lese = [str(p.get("problem", "")).strip() for p in data.get("lese_probleme", [])
|
||
if isinstance(p, dict) and str(p.get("problem", "")).strip()]
|
||
return {"claims": claims, "ziele": ziele, "luecken": luecken, "ballast": ballast,
|
||
"lese_probleme": lese}
|
||
|
||
|
||
def _first_section(md: str) -> dict | None:
|
||
secs = _parse_fragment(md) if md else []
|
||
return secs[0] if secs else None
|
||
|
||
|
||
class _Env:
|
||
"""Shared per-run context for the card tasks."""
|
||
|
||
def __init__(self, ctx, guide_id, topic, format_name, instructions, content_path,
|
||
subs_by_title, chapter_map, fallback_facts, spec):
|
||
self.ctx = ctx
|
||
self.guide_id = guide_id
|
||
self.topic = topic
|
||
self.format = format_name
|
||
self.instructions = instructions
|
||
self.content_path = content_path
|
||
self.subs_by_title = subs_by_title # block title → [sub dicts]
|
||
self.chapter_map = chapter_map # block_norm → (chapter title, ord)
|
||
self.fallback_facts = fallback_facts # generic source hint (legacy topics without facts)
|
||
self.spec = spec
|
||
|
||
def slot(self, name: str):
|
||
return self.content_path.parent / f"{self.content_path.stem}.{name}"
|
||
|
||
|
||
def _card_facts(env: _Env, block_title: str) -> str:
|
||
from guide import _facts_grounding # lazy: guide imports this module
|
||
grounding = _facts_grounding({block_title: env.subs_by_title.get(block_title, [])})
|
||
return grounding or env.fallback_facts
|
||
|
||
|
||
async def _card_examples(env: _Env, block_norm: str, subs: list[dict],
|
||
include_unmatched: bool = True) -> str:
|
||
"""Verified worked examples of the block as writer input, matched to `subs` via
|
||
sub_norm (a split half gets only its own). Rows whose sub does not match (generation
|
||
mismatch) go to the full writer / split part 1 so they never vanish silently."""
|
||
rows = await db.get_sub_artefakte(env.topic, type="example", block_norm=block_norm)
|
||
if not rows:
|
||
return ""
|
||
wanted = {_norm_title(s["title"]) for s in subs}
|
||
out = []
|
||
for r in rows:
|
||
matched = r["sub_norm"] in wanted
|
||
if not matched and not include_unmatched:
|
||
continue
|
||
data = json.loads(r["data"]) if isinstance(r["data"], str) else (r["data"] or {})
|
||
steps = " ".join(f"{i}) {s}" for i, s in enumerate(data.get("steps") or [], 1))
|
||
where = (f"Subbaustein „{r['sub_title']}“" if matched
|
||
else "Subbaustein unklar — dort einweben, wo es fachlich passt")
|
||
out.append(f"- {where}:\n Problem: {data.get('problem', '')}\n"
|
||
f" Schritte: {steps}\n Ergebnis: {data.get('result', '')}")
|
||
if not out:
|
||
return ""
|
||
return ("VERIFIED WORKED EXAMPLES (already fact-checked; each belongs to ONE subblock):\n"
|
||
+ "\n".join(out) + "\n"
|
||
"Weave each example into the ausführlich text of EXACTLY its subblock, right "
|
||
"after the concept it applies has been explained — as a short worked-through "
|
||
"passage (problem → steps → result recognizable, flowing prose or a compact "
|
||
"numbered list). Take all values and results over VERBATIM, never recompute "
|
||
"or alter them. NEVER put examples into the compact layer. Subblocks without "
|
||
"an example get none.")
|
||
|
||
|
||
def _card_assignment(env: _Env, card: dict) -> str:
|
||
from guide import _level_label
|
||
lines = [f"- {card['block']}"]
|
||
for s in env.subs_by_title.get(card["block"], []):
|
||
lines.append(f" [{_level_label(s)}] {s['title']}")
|
||
return "\n".join(lines)
|
||
|
||
|
||
# Live info per active card (in-memory): what the card is doing RIGHT NOW —
|
||
# board_snapshot shows it as the info line while status == active.
|
||
_live_info: dict[tuple[str, str, str], str] = {}
|
||
|
||
|
||
def _live(env: _Env, card: dict, msg: str) -> None:
|
||
_live_info[(env.topic, env.format, card["block_norm"])] = msg
|
||
|
||
|
||
async def _set(env: _Env, card: dict, **fields):
|
||
card.update(fields)
|
||
await db.set_guide_card(env.topic, env.format, card["block_norm"], **fields)
|
||
|
||
|
||
# ── Stages ─────────────────────────────────────────────────────────────────────────
|
||
async def _stage_lernziele(env: _Env, card: dict) -> bool:
|
||
norm = card["block_norm"]
|
||
if not await db.list_lernziele(env.topic, norm):
|
||
subs = "\n".join(f"- [{s.get('level', 'beginner')}] {s['title']}"
|
||
for s in env.subs_by_title.get(card["block"], [])) or "(keine)"
|
||
|
||
async def _versuch(suffix: str):
|
||
path = env.slot(f"ziele-{_safe(norm)}{suffix}.json")
|
||
return await run_single_slot(
|
||
env.ctx, f"Lernziele {card['block']}", key=f"{env.guide_id}-ziele-{_safe(norm)}{suffix}",
|
||
prompt=_prompt("Guide-Lernziele", topic=env.topic, block=card["block"],
|
||
subs=subs, facts=_card_facts(env, card["block"]),
|
||
out_path=path, extra=_extra(env.instructions)),
|
||
role="judge", capabilities="files",
|
||
payload=lambda result, p=path: _ziele_schema(_json_file(p)),
|
||
timeout=_timeout("lernziele", len(env.subs_by_title.get(card["block"], []))))
|
||
|
||
status, ziele = await _versuch("")
|
||
if status == CANCELLED:
|
||
return False
|
||
if status == FAILED:
|
||
await _set(env, card, status="error", gate_info="Lernziele ohne Ergebnis")
|
||
return False
|
||
if not ziele: # ein Ersatz-Versuch — leere Liste heißt: das Coverage-Gate läuft leer
|
||
status, ziele = await _versuch("-2")
|
||
if status == CANCELLED:
|
||
return False
|
||
if not isinstance(ziele, list):
|
||
ziele = []
|
||
if not ziele:
|
||
_log(env.topic, f"Lernziele {card['block']}: zweimal leer — Block ohne Coverage-Gate")
|
||
for z in ziele:
|
||
await db.put_lernziel(env.topic, norm, z["id"], z["text"], _norm_title(z["sub"]))
|
||
await _set(env, card, stage="zuweisung", status="open")
|
||
return True
|
||
|
||
|
||
async def _stage_zuweisung(env: _Env, card: dict) -> bool:
|
||
chapter, ord_ = env.chapter_map.get(card["block_norm"], ("Weitere Inhalte", 10_000))
|
||
await _set(env, card, chapter=chapter, ord=ord_, stage="writer")
|
||
return True
|
||
|
||
|
||
# A single section over ~45 subs measurably breaks the writer/coverage (Front Matter:
|
||
# 4/6 objectives open after 2 rounds). First drafts of oversized cards are written in two
|
||
# halves and merged back into ONE canonical section (all gates/assembly read one section).
|
||
# WRITER_SPLIT_SUBS: siehe config.py
|
||
|
||
|
||
def _merge_split_sections(sec_a: dict, sec_b: dict) -> str:
|
||
"""Rebuild ONE canonical fragment from two half-sections: header + anchor from part A,
|
||
sub blocks of both parts in order, both layers. Part B's framing is dropped — its
|
||
prompt forbids an intro; keeping it would inject a second lead-in mid-section."""
|
||
lines = []
|
||
if sec_a.get("chapters"):
|
||
lines.append(f"<!-- kapitel: {sec_a['chapters']} -->")
|
||
lines.append(f"<!-- section: {sec_a['title']} -->")
|
||
lines.append("<!-- compact -->")
|
||
if sec_a.get("anker_compact"):
|
||
lines.append(sec_a["anker_compact"])
|
||
for sub in [*sec_a["subs"], *sec_b["subs"]]:
|
||
if sub.get("compact"):
|
||
lines.append(f"<!-- sub: {sub['level']} | {sub['title']} -->")
|
||
lines.append(sub["compact"])
|
||
lines.append("<!-- ausführlich -->")
|
||
if sec_a.get("anchor"):
|
||
lines.append(sec_a["anchor"])
|
||
for sub in [*sec_a["subs"], *sec_b["subs"]]:
|
||
if sub.get("md"):
|
||
lines.append(f"<!-- sub: {sub['level']} | {sub['title']} -->")
|
||
lines.append(sub["md"])
|
||
return "\n\n".join(lines)
|
||
|
||
|
||
async def _write_split(env: _Env, card: dict, ziele_text: str):
|
||
"""First draft in two halves (parallel), merged into one section.
|
||
→ merged text | None (failed) | False (cancelled)."""
|
||
from guide import _level_label
|
||
norm = card["block_norm"]
|
||
subs = env.subs_by_title.get(card["block"], [])
|
||
half = (len(subs) + 1) // 2
|
||
parts = (subs[:half], subs[half:])
|
||
hints = (
|
||
"TEIL 1/2: Schreibe den Abschnitts-EINSTIEG und die folgenden Unterpunkte. "
|
||
"Weitere Unterpunkte folgen in Teil 2 — KEIN Fazit, KEIN Ausblick am Ende.",
|
||
"TEIL 2/2: FORTSETZUNG desselben Abschnitts. KEIN neuer Einstieg, KEINE "
|
||
"Wiederholung von Teil 1 — direkt mit den Unterpunkten weitermachen.",
|
||
)
|
||
|
||
async def _one(i):
|
||
assignment = "\n".join([f"- {card['block']}"]
|
||
+ [f" [{_level_label(s)}] {s['title']}" for s in parts[i]])
|
||
path = env.slot(f"card-{_safe(norm)}-r0-{'ab'[i]}.md")
|
||
path.unlink(missing_ok=True)
|
||
|
||
def _payload(result, p=path):
|
||
t = p.read_text(encoding="utf-8") if p.exists() else ""
|
||
sec = _first_section(t)
|
||
return t if sec and sec.get("md", "").strip() else None
|
||
|
||
return await run_single_slot(
|
||
env.ctx, f"Writer {card['block']} ({i + 1}/2)",
|
||
key=f"{env.guide_id}-w-{_safe(norm)}-r0-{'ab'[i]}",
|
||
prompt=_prompt("Guide-Writer-Board", topic=env.topic, format_name=env.format,
|
||
chapter=card.get("chapter") or "Inhalte",
|
||
assignment=assignment, ziele=ziele_text,
|
||
facts=_card_facts(env, card["block"]),
|
||
examples=await _card_examples(env, norm, parts[i],
|
||
include_unmatched=(i == 0)),
|
||
gaps="\n" + hints[i] + "\n",
|
||
budget=block_budget(parts[i]),
|
||
spec=env.spec, out_path=path, extra=_extra(env.instructions)),
|
||
role="guide", capabilities="files", payload=_payload,
|
||
timeout=_timeout("writer", 1))
|
||
|
||
results = await asyncio.gather(_one(0), _one(1))
|
||
if any(s == CANCELLED for s, _ in results):
|
||
return False
|
||
if any(s == FAILED for s, _ in results):
|
||
return None
|
||
return _merge_split_sections(_first_section(results[0][1]), _first_section(results[1][1]))
|
||
|
||
|
||
async def _stage_writer(env: _Env, card: dict) -> bool:
|
||
norm = card["block_norm"]
|
||
ziele = await db.list_lernziele(env.topic, norm)
|
||
ziele_text = "\n".join(f"- ({z['ziel_id']}) {z['text']}" for z in ziele) or "(keine definiert)"
|
||
# oversized first drafts: two halves, merged into one canonical section
|
||
if card["writer_rounds"] == 0 and len(env.subs_by_title.get(card["block"], [])) > WRITER_SPLIT_SUBS:
|
||
text = await _write_split(env, card, ziele_text)
|
||
if text is False:
|
||
return False
|
||
if text is None:
|
||
await _set(env, card, status="error", gate_info="Writer (Split) ohne Ergebnis")
|
||
return False
|
||
await _set(env, card, md=text, stage="pruefer", status="open")
|
||
return True
|
||
|
||
path = env.slot(f"card-{_safe(norm)}-r{card['writer_rounds']}.md")
|
||
path.unlink(missing_ok=True)
|
||
|
||
def _payload(result):
|
||
text = path.read_text(encoding="utf-8") if path.exists() else ""
|
||
sec = _first_section(text)
|
||
return text if sec and sec.get("md", "").strip() else None
|
||
|
||
status, text = await run_single_slot(
|
||
env.ctx, f"Writer {card['block']}", key=f"{env.guide_id}-w-{_safe(norm)}-r{card['writer_rounds']}",
|
||
prompt=_prompt("Guide-Writer-Board", topic=env.topic, format_name=env.format,
|
||
chapter=card.get("chapter") or "Inhalte",
|
||
assignment=_card_assignment(env, card), ziele=ziele_text,
|
||
facts=_card_facts(env, card["block"]),
|
||
examples=await _card_examples(env, norm, env.subs_by_title.get(card["block"], [])),
|
||
gaps="", spec=env.spec,
|
||
budget=block_budget(env.subs_by_title.get(card["block"], [])),
|
||
out_path=path, extra=_extra(env.instructions)),
|
||
role="guide", capabilities="files", payload=_payload,
|
||
timeout=_timeout("writer", 1))
|
||
if status == CANCELLED:
|
||
return False
|
||
if status == FAILED:
|
||
await _set(env, card, status="error", gate_info="Writer ohne Ergebnis")
|
||
return False
|
||
await _set(env, card, md=text, stage="pruefer", status="open")
|
||
return True
|
||
|
||
|
||
def _n_rel(env: _Env, card: dict) -> int:
|
||
return sum(1 for s in env.subs_by_title.get(card["block"], [])
|
||
if s.get("relevance") != "peripheral")
|
||
|
||
|
||
def _det_hinweise(env: _Env, card: dict, sec: dict) -> list[str]:
|
||
"""Deterministische Befunde (extern geerdet, kein LLM): Readability-Modell +
|
||
Längenbudget — dieselbe Formel wie der QA-Detektor (guide_qa.block_budget), nur mit
|
||
engerem Band, damit der Fix VOR der QA-Grenze greift. Gehen direkt in den Fix
|
||
und als „nicht wiederholen"-Notiz in den Prüfer-Prompt."""
|
||
out: list[str] = []
|
||
subs_all = env.subs_by_title.get(card["block"], [])
|
||
if not any(s.get("relevance") != "peripheral" for s in subs_all):
|
||
return out # kein Inventar als Budget-Basis → kein Längen-Urteil (wie der QA-Detektor)
|
||
budget = block_budget(subs_all)
|
||
aus = re.split(r"<!--\s*ausführlich\s*-->", sec["md"], maxsplit=1)
|
||
zeichen = len(aus[1] if len(aus) == 2 else sec["md"])
|
||
if not (0.5 * budget <= zeichen <= 1.2 * budget):
|
||
out.append(
|
||
f"Länge {zeichen} Zeichen (Budget {budget}, erlaubt {round(0.5 * budget)}–{round(1.2 * budget)}): "
|
||
f"schreibe den ausführlich-Teil auf etwa {budget} Zeichen GESAMT um — Sockel-Prosa und "
|
||
f"Wiederholungen streichen, alle Sub-Marker und Beispiele behalten")
|
||
return out
|
||
|
||
|
||
async def _det_readability(sec: dict) -> list[str]:
|
||
if not READABILITY_ACTIVE:
|
||
return []
|
||
hints = await asyncio.to_thread(readability.rate_sections, {1: sec["md"]})
|
||
return [hints[1]] if hints.get(1) else []
|
||
|
||
|
||
def _auftraege(verdict: dict, det: list[str], n_rel: int = 0) -> tuple[list[str], bool]:
|
||
"""Prüfer-Verdikt → Fix-Auftragszeilen. kritisch = falsch-Claims oder Lücken
|
||
(nur die rechtfertigen den Re-Prüfer-Pass — Fakten/Coverage sind der Qualitätskern).
|
||
Claims-Schwelle: wenige nur-„unbelegt" lohnen keinen Fix-Pass — bei kleinen Sektionen
|
||
sinkt sie auf die Sub-Zahl (2 unbelegte Claims in 2 Subs sind viel, nicht wenig)."""
|
||
claims = verdict["claims"]
|
||
falsch = [c for c in claims if c["urteil"] == "falsch"]
|
||
schwelle = min(GATE_FIX_MIN, n_rel) if n_rel else GATE_FIX_MIN
|
||
if claims and not falsch and len(claims) < schwelle:
|
||
claims = []
|
||
zeilen = [f"- CLAIM ({c['urteil']}): {c['text']}" + (f" — {c['grund']}" if c['grund'] else "")
|
||
for c in claims]
|
||
zeilen += [f"- LÜCKE ({l['ziel']}): {l['fehlt']}" for l in verdict["luecken"]]
|
||
zeilen += [f"- BALLAST (kürzen): {b}" for b in verdict["ballast"]]
|
||
zeilen += [f"- LESBARKEIT: {p}" for p in verdict["lese_probleme"]]
|
||
zeilen += [f"- LESBARKEIT: {p}" for p in det]
|
||
return zeilen, bool(falsch or verdict["luecken"])
|
||
|
||
|
||
async def _pruefer_call(env: _Env, card: dict, sec: dict, tag: str, det: list[str]) -> dict | None:
|
||
"""EIN Judge-Call prüft Fakten + Coverage + Lesbarkeit (die drei lasen vorher denselben
|
||
Section-Text in drei seriellen Calls). Text-Antwort + Engine-Sink (Datei-schreibende
|
||
Judges lieferten invalides JSON). → Verdikt | None (FAILED/CANCELLED)."""
|
||
norm = card["block_norm"]
|
||
ziele = await db.list_lernziele(env.topic, norm)
|
||
ziele_text = "\n".join(f"- ({z['ziel_id']}) {z['text']}" for z in ziele) or "(keine definiert)"
|
||
ids = {z["ziel_id"] for z in ziele}
|
||
facts = _card_facts(env, card["block"])
|
||
ex = await _card_examples(env, norm, env.subs_by_title.get(card["block"], []))
|
||
if ex: # der Fix sieht dieselben Facts — Beispiele überleben den Fix-Pass
|
||
facts += "\n\nVERIFIED WORKED EXAMPLES (count as verified facts for this check):\n" + ex
|
||
hinweise = ("\nALREADY NOTED deterministically (do NOT repeat, they go to the fix anyway):\n"
|
||
+ "\n".join(f"- {d}" for d in det) + "\n") if det else "\n"
|
||
path = env.slot(f"pruefer-{_safe(norm)}-{tag}.json")
|
||
status, verdict = await run_single_slot(
|
||
env.ctx, f"Prüfer {card['block']}", key=f"{env.guide_id}-pruef-{_safe(norm)}-{tag}",
|
||
prompt=_prompt("Guide-Pruefer", topic=env.topic, block=card["block"],
|
||
section=sec["md"], facts=facts, ziele=ziele_text, spec=env.spec,
|
||
hinweise=hinweise, extra=_extra(env.instructions)),
|
||
role="judge", capabilities="none",
|
||
payload=lambda result: _sink_json(result, path, lambda d: _pruefer_schema(d, ids)),
|
||
timeout=_timeout("fakten_gate", 1))
|
||
if status != OK or verdict is None:
|
||
return None
|
||
for zid, ok in verdict["ziele"].items():
|
||
if zid in ids:
|
||
await db.set_ziel_covered(env.topic, norm, zid, ok)
|
||
return verdict
|
||
|
||
|
||
async def _stage_pruefer(env: _Env, card: dict) -> bool:
|
||
"""Verschmolzener Qualitäts-Pass: Fakten-Gate + Coverage + Lese-Check in EINEM Call
|
||
(vorher 3 serielle Judges + bis zu 3 Edit-Pässe, die einander überschrieben und deren
|
||
letzter ungeprüft blieb). Befunde → Fix-Stage; ohne Befund → done."""
|
||
sec = _first_section(card["md"])
|
||
if sec is None:
|
||
await _set(env, card, status="error", gate_info="Writer-Fragment unlesbar")
|
||
return False
|
||
det = (await _det_readability(sec)) + _det_hinweise(env, card, sec)
|
||
verdict = await _pruefer_call(env, card, sec, f"r{card['writer_rounds']}", det)
|
||
if verdict is None:
|
||
if is_guide_cancelled(env.guide_id):
|
||
return False
|
||
# fail-open wie das alte Gate: Karte nie blockieren — deterministische Befunde
|
||
# gehen trotzdem in den Fix
|
||
_log(env.topic, f"Prüfer {card['block']}: kein Ergebnis — nur deterministische Checks")
|
||
verdict = {"claims": [], "ziele": {}, "luecken": [], "ballast": [], "lese_probleme": []}
|
||
zeilen, kritisch = _auftraege(verdict, det, _n_rel(env, card))
|
||
if not zeilen:
|
||
await _set(env, card, md=card["md"], stage="done", status="ok", gate_info="")
|
||
return True
|
||
_log(env.topic, f"Prüfer {card['block']}: {len(zeilen)} Befund(e){' (kritisch)' if kritisch else ''} → Fix")
|
||
await _set(env, card, gate_info=("KRITISCH\n" if kritisch else "") + "\n".join(zeilen),
|
||
stage="fix", status="open")
|
||
return True
|
||
|
||
|
||
async def _stage_fix(env: _Env, card: dict) -> bool:
|
||
"""EIN kompletter Section-Rewrite unter allen Auflagen (ersetzt Fakten-Fix +
|
||
Writer-Revision + Lese-Fix). Danach GENAU EIN Re-Prüfer-Pass, wenn der Fix wegen
|
||
falsch-Claims/Lücken lief — der alte Lese-Fix blieb ungeprüft. Rest-Befunde bleiben
|
||
sichtbar (gate_info), keine weitere Fix-Runde."""
|
||
from guide import _level_label
|
||
norm = card["block_norm"]
|
||
sec = _first_section(card["md"])
|
||
if sec is None:
|
||
await _set(env, card, status="error", gate_info="Fragment unlesbar")
|
||
return False
|
||
info = card.get("gate_info") or ""
|
||
kritisch = info.startswith("KRITISCH\n")
|
||
auftraege = info.removeprefix("KRITISCH\n")
|
||
subs = env.subs_by_title.get(card["block"], [])
|
||
sub_list = "\n".join(f"- [{_level_label(s)}] {s['title']}" for s in subs) or "(none)"
|
||
fixp = env.slot(f"fix-{_safe(norm)}-r{card['writer_rounds']}.md")
|
||
fixp.unlink(missing_ok=True)
|
||
|
||
def _fixload(result):
|
||
text = fixp.read_text(encoding="utf-8") if fixp.exists() else ""
|
||
return text if _first_section(text) else None
|
||
|
||
fstatus, fixed = await run_single_slot(
|
||
env.ctx, f"Fix {card['block']}", key=f"{env.guide_id}-gfix-{_safe(norm)}-r{card['writer_rounds']}",
|
||
prompt=_prompt("Guide-Fix", topic=env.topic, format_name=env.format, block=card["block"],
|
||
section=card["md"], facts=_card_facts(env, card["block"]), spec=env.spec,
|
||
auftraege=auftraege, sub_list=sub_list, out_path=fixp,
|
||
extra=_extra(env.instructions)),
|
||
role="guide", capabilities="files", payload=_fixload,
|
||
timeout=_timeout("writer", 1))
|
||
if fstatus == CANCELLED:
|
||
return False
|
||
angewandt = False
|
||
if fstatus == OK and fixed:
|
||
new_sec = _first_section(fixed)
|
||
# marker invariant: a fix that loses the sub markers kills the level filter → discard
|
||
if sec.get("subs") and not (new_sec and new_sec.get("subs")):
|
||
_log(env.topic, f"Fix {card['block']} ohne Sub-Marker — verworfen")
|
||
else:
|
||
card["md"] = fixed
|
||
angewandt = True
|
||
rest = ""
|
||
if kritisch and angewandt:
|
||
sec2 = _first_section(card["md"])
|
||
verdict = await _pruefer_call(env, card, sec2, "re", [])
|
||
if verdict is None and is_guide_cancelled(env.guide_id):
|
||
return False
|
||
if verdict:
|
||
zeilen, _k = _auftraege(verdict, [], _n_rel(env, card))
|
||
if zeilen:
|
||
rest = "Rest-Befunde nach Fix:\n" + "\n".join(zeilen)
|
||
_log(env.topic, f"Re-Prüfer {card['block']}: {len(zeilen)} Rest-Befund(e) bleiben")
|
||
await _set(env, card, md=card["md"], stage="done", status="ok", gate_info=rest)
|
||
return True
|
||
|
||
|
||
_STAGE_FN = {"lernziele": _stage_lernziele, "zuweisung": _stage_zuweisung,
|
||
"writer": _stage_writer, "pruefer": _stage_pruefer, "fix": _stage_fix}
|
||
|
||
|
||
async def _run_card(env: _Env, card: dict, sem: asyncio.Semaphore) -> None:
|
||
async with sem:
|
||
try:
|
||
await _run_card_inner(env, card)
|
||
finally:
|
||
_live_info.pop((env.topic, env.format, card["block_norm"]), None)
|
||
|
||
|
||
async def _run_card_inner(env: _Env, card: dict) -> None:
|
||
while card["stage"] != "done":
|
||
if is_guide_cancelled(env.guide_id):
|
||
await _set(env, card, status="open") # no longer being worked
|
||
return
|
||
fn = _STAGE_FN.get(card["stage"])
|
||
if fn is None: # unknown stage → park as error
|
||
await _set(env, card, status="error", gate_info=f"Unbekannte Stage {card['stage']}")
|
||
return
|
||
if card["status"] != "active":
|
||
await _set(env, card, status="active") # live board: this card is being worked
|
||
_live(env, card, STAGE_LABELS.get(card["stage"], card["stage"]) + "…")
|
||
try:
|
||
if not await fn(env, card):
|
||
return
|
||
except Exception as e:
|
||
log.exception("[%s] guide card %s failed", env.topic, card["block"])
|
||
await _set(env, card, status="error", gate_info=f"{type(e).__name__}: {e}"[:300])
|
||
return
|
||
|
||
|
||
# ── Orchestration ──────────────────────────────────────────────────────────────────
|
||
async def _chapter_map(topic: str, entries: dict[int, str]) -> dict[str, tuple[str, int]]:
|
||
"""block_norm → (chapter title, global order) from the outline artefact."""
|
||
from guide import _outline_from_db, _fallback_outline, _with_remainder
|
||
plan = await _outline_from_db(topic, entries) or _fallback_outline(entries)
|
||
plan = _with_remainder(plan, entries)
|
||
out: dict[str, tuple[str, int]] = {}
|
||
i = 0
|
||
for ch in plan:
|
||
for num in ch.get("nums", []):
|
||
if num in entries:
|
||
out[_norm_title(_title(entries[num]))] = (ch.get("title") or "Kapitel", i)
|
||
i += 1
|
||
return out
|
||
|
||
|
||
async def run_guide_board(guide_id: str, topic: str, format_name: str, entries: dict[int, str],
|
||
instructions: str, provider: str, content_path) -> list[dict] | None:
|
||
"""Seed one card per block (existing cards keep their stage — resume), run all cards,
|
||
assemble the chapters in the legacy content format. → chapters | None (cancel/empty)."""
|
||
from blocks import source_folder
|
||
from guide import _load_subblocks
|
||
ctx = GenContext(topic=topic, provider=provider,
|
||
is_cancelled=lambda: is_guide_cancelled(guide_id), guide_id=guide_id)
|
||
import uuid
|
||
from datetime import datetime, timezone
|
||
db.set_current_run(topic, f"{datetime.now(timezone.utc).strftime('%Y%m%d-%H%M')}-g{uuid.uuid4().hex[:4]}")
|
||
try:
|
||
spec = (TEMPLATES_DIR / "Format" / "Section.md").read_text(encoding="utf-8")
|
||
subs_raw = await _load_subblocks(topic)
|
||
project = source_folder(topic)
|
||
fallback = (_prompt("Guide-Facts-Projekt", project=project) if project
|
||
else _prompt("Guide-Facts-Thema"))
|
||
env = _Env(ctx, guide_id, topic, format_name, instructions, content_path,
|
||
subs_raw, await _chapter_map(topic, entries), fallback, spec)
|
||
for num, line in entries.items():
|
||
title = _title(line)
|
||
await db.upsert_guide_card(topic, format_name, _norm_title(title), title)
|
||
cards = await db.list_guide_cards(topic, format_name)
|
||
open_cards = [c for c in cards if c["stage"] != "done"]
|
||
if open_cards:
|
||
sem = asyncio.Semaphore(CARD_CONCURRENCY)
|
||
|
||
async def _progress():
|
||
while True:
|
||
counts = await db.guide_stage_counts(topic, format_name)
|
||
done = counts.get("done", 0)
|
||
total = sum(counts.values())
|
||
await db.update_guide(guide_id, progress=f"Board: {done}/{total} Karten fertig")
|
||
await asyncio.sleep(2.0)
|
||
|
||
reporter = asyncio.create_task(_progress())
|
||
try:
|
||
await asyncio.gather(*[_run_card(env, c, sem) for c in open_cards])
|
||
finally:
|
||
reporter.cancel()
|
||
if is_guide_cancelled(guide_id):
|
||
return None
|
||
# assembly — identical shape to the legacy pipeline
|
||
cards = await db.list_guide_cards(topic, format_name)
|
||
chapters: list[dict] = []
|
||
by_chapter: dict[str, list[dict]] = {}
|
||
order: list[str] = []
|
||
for c in sorted(cards, key=lambda c: (c["ord"], c["block_norm"])):
|
||
if c["stage"] != "done":
|
||
_log(topic, f"Guide: Karte '{c['block']}' nicht fertig ({c['stage']}) — Abschnitt fehlt")
|
||
continue
|
||
sec = _first_section(c["md"])
|
||
if sec is None:
|
||
continue
|
||
ch = c["chapter"] or "Inhalte"
|
||
if ch not in by_chapter:
|
||
by_chapter[ch] = []
|
||
order.append(ch)
|
||
by_chapter[ch].append({
|
||
"num": c["ord"], "title": c["block"], "md": sec["md"],
|
||
"compact": sec.get("compact", ""), "anchor": sec.get("anchor", ""),
|
||
"anker_compact": sec.get("anker_compact", ""), "subs": sec.get("subs", []),
|
||
"checkable": format_name == "Guide" or bool(
|
||
any(s.get("relevance") == "relevant" for s in subs_raw.get(c["block"], []))),
|
||
})
|
||
for ch in order:
|
||
chapters.append({"title": ch, "sections": by_chapter[ch]})
|
||
if chapters:
|
||
try: # Abschluss-Guide-QA (best-effort): speist das Badge mit einer frischen Note
|
||
import guide_qa
|
||
rep = await guide_qa.guide_qa_report(topic, llm=True)
|
||
if rep:
|
||
await asyncio.to_thread(guide_qa._write_report, rep)
|
||
except Exception:
|
||
log.exception("[%s] Abschluss-Guide-QA fehlgeschlagen", topic)
|
||
return chapters or None
|
||
finally:
|
||
# erst NACH der Abschluss-Guide-QA leeren: deren Judge-Events gehören zum
|
||
# Lauf — vorher fielen sie ohne run_id aus jeder Run-Aggregation
|
||
db.set_current_run(topic, None)
|
||
|
||
|
||
async def done_step(topic: str, format_name: str) -> int:
|
||
"""Sidebar dots: highest fully completed stage index. -1 = nothing, len(stages) at done."""
|
||
counts = await db.guide_stage_counts(topic, format_name)
|
||
if not counts:
|
||
return -1
|
||
if set(counts) == {"done"}:
|
||
return len(GUIDE_STAGES)
|
||
lowest = min(GUIDE_STAGES.index(s) for s in counts if s in GUIDE_STAGES)
|
||
return lowest - 1 if lowest > 0 else -1
|
||
|
||
|
||
async def board_snapshot(topic: str, format_name: str, limit: int = 20) -> dict:
|
||
"""Live guide board: columns with counts + cards (title, rounds, covered objectives)."""
|
||
cards = await db.list_guide_cards(topic, format_name)
|
||
ziele = {}
|
||
for z in await db.list_lernziele(topic):
|
||
d = ziele.setdefault(z["block_norm"], [0, 0])
|
||
d[1] += 1
|
||
d[0] += 1 if z["covered"] else 0
|
||
columns = []
|
||
for stage in (*GUIDE_STAGES, "done"):
|
||
in_stage = [c for c in cards if c["stage"] == stage]
|
||
views = []
|
||
for c in in_stage[:limit]:
|
||
zc = ziele.get(c["block_norm"])
|
||
info = c["gate_info"][:200] if c["status"] == "error" else ""
|
||
if c["status"] == "active":
|
||
info = _live_info.get((topic, format_name, c["block_norm"]), "") or info
|
||
views.append({"title": c["block"], "card_id": c["block_norm"],
|
||
"status": c["status"] if c["status"] in ("error", "active") else "open",
|
||
"rounds": c["writer_rounds"],
|
||
"info": info,
|
||
"ziele": f"{zc[0]}/{zc[1]}" if zc else ""})
|
||
columns.append({"key": stage, "label": STAGE_LABELS[stage],
|
||
"total": len(in_stage), "cards": views})
|
||
import qa as qa_mod # lazy wie in board_inventory
|
||
tdir = qa_mod.QA_DIR / topic
|
||
greports = sorted(tdir.glob("guide-*.json"), key=lambda p: p.stat().st_mtime) if tdir.is_dir() else []
|
||
note_guide = (_json_file(greports[-1]) or {}).get("note_guide") if greports else None
|
||
return {"columns": columns, "qa_guide": note_guide}
|
||
|
||
|
||
async def repair_karten(topic: str, format_name: str) -> list[str]:
|
||
"""QA-Befund-getriebenes Guide-Repair: Karten, die im jüngsten Guide-QA-Report
|
||
Befunde tragen, gehen zurück auf `pruefer` (md bleibt) — Prüfer+Fix beheben gezielt,
|
||
generate_guide resumt die offenen Karten und misst am Ende neu. Pendant zum
|
||
Blocks-Repair („Score unter 10 muss einen Fix-Pfad haben"). → betroffene Blocktitel."""
|
||
import qa as qa_mod
|
||
tdir = qa_mod.QA_DIR / topic
|
||
reports = sorted(tdir.glob("guide-*.json"), key=lambda p: p.stat().st_mtime) if tdir.is_dir() else []
|
||
rep = _json_file(reports[-1]) if reports else None
|
||
if not rep:
|
||
return []
|
||
cards = {c["block_norm"]: c for c in await db.list_guide_cards(topic, format_name)}
|
||
norms: set[str] = set()
|
||
for e in rep.get("marker_fehlend", []): # "Block · sub"
|
||
norms.add(_norm_title(str(e).split(" · ")[0]))
|
||
for e in rep.get("ziel_ohne_anker", []): # "block_norm · (id) text"
|
||
norms.add(str(e).split(" · ")[0])
|
||
for e in rep.get("laengen_ausreisser", []): # {"block": titel}
|
||
norms.add(_norm_title(e.get("block", "") if isinstance(e, dict) else str(e)))
|
||
for e in rep.get("lesbarkeit", []): # "Block: hinweis"
|
||
norms.add(_norm_title(str(e).split(":")[0]))
|
||
for t in rep.get("fachlich_falsch", []) or []:
|
||
norms.add(_norm_title(str(t)))
|
||
for e in rep.get("redundanz", []): # {"a": "Block: absatz", "b": …}
|
||
for seite in ("a", "b"):
|
||
norms.add(_norm_title(str(e.get(seite, "")).split(":")[0]))
|
||
betroffen = []
|
||
for n in sorted(norms & set(cards)):
|
||
await db.set_guide_card(topic, format_name, n, stage="pruefer", status="open", gate_info="")
|
||
betroffen.append(cards[n]["block"])
|
||
return betroffen
|
||
|
||
|
||
async def reset_card(topic: str, format_name: str, block_norm: str, ab_stage: int) -> bool:
|
||
"""Reset ONE guide card to a stage (single-card variant of reset_from_stage):
|
||
fields re-zeroed, md only wiped for writer(2) and earlier, lernziele only for 0."""
|
||
ab_stage = max(0, min(ab_stage, len(GUIDE_STAGES) - 1))
|
||
cards = {c["block_norm"]: c for c in await db.list_guide_cards(topic, format_name)}
|
||
if block_norm not in cards:
|
||
return False
|
||
fields = dict(stage=GUIDE_STAGES[ab_stage], status="open", writer_rounds=0, gate_info="")
|
||
if ab_stage <= 2:
|
||
fields["md"] = ""
|
||
if ab_stage == 0:
|
||
await db.delete_lernziele(topic, block_norm)
|
||
await db.set_guide_card(topic, format_name, block_norm, **fields)
|
||
return True
|
||
|
||
|
||
async def reset_from_stage(topic: str, format_name: str, ab_stage: int) -> int:
|
||
"""Cards in stages ≥ ab_stage (incl. done) back to GUIDE_STAGES[ab_stage]."""
|
||
ab_stage = max(0, min(ab_stage, len(GUIDE_STAGES) - 1))
|
||
target = GUIDE_STAGES[ab_stage]
|
||
stages = list(GUIDE_STAGES[ab_stage:]) + ["done"]
|
||
if ab_stage == 0:
|
||
for c in await db.list_guide_cards(topic, format_name):
|
||
await db.delete_lernziele(topic, c["block_norm"])
|
||
moved = await db.reset_guide_cards_from_stage(topic, format_name, stages, target,
|
||
clear_md=ab_stage <= 2)
|
||
return moved
|